Search Results (81)

Rising complexity in cyber-physical systems development exposes challenges in the consistent and reusable specification of graphical domain-specific languages (DSLs). Despite the benefits of model-based systems engineering (MBSE), the absence of a standardized, life-cycle-wide specification process results in semantic inconsistencies, tool dependence, and limited interoperability. While our previous work has addressed individual stages of DSL definition, a comprehensive, standards-based process integrating these stages remains missing. Building on these foundations, this paper introduces a unified language specification process for graphical DSLs grounded in established standards—the Meta-Object Facility (MOF), Unified Modeling Language (UML), Web Ontology Language (OWL), and Resource Description Framework (RDF). The process integrates three core artifacts: a tool-independent ontology capturing domain semantics, a MOF-conforming metamodel unifying abstract syntax, semantics, and concrete syntax, and a UML-profile-based implementation. To support and exemplify this process, a prototypical toolchain is introduced that enables automated transformations between these artifacts, thereby facilitating the consistent propagation of semantics from ontology to implementation. The applicability of the proposed process is demonstrated through both a top-down automotive case and a bottom-up cybersecurity DSL, illustrating its cross-domain generalizability. By explicitly structuring and connecting ontology, metamodel, and implementation, this work contributes a semantically consistent, machine-interpretable, and tool-independent specification process for graphical DSLs in MBSE. Full article

Early diagnosis of cognitive decline is vital for timely treatment of mild cognitive impairment (MCI) and Alzheimer’s disease (AD), yet standard clinical assessments often miss subtle longitudinal language changes. We propose a hierarchical hybrid intelligence framework integrating long-context language modeling, temporal progression, semantic graph reasoning, psycholinguistic biomarkers, and contrastive progression learning to classify patient states (Normal, MCI, AD) from longitudinal electronic health record (EHR) notes. The model was trained on 4500 patients and 68,000 clinical notes from Medical Information Mart for Intensive Care III (MIMIC-III) and externally validated on the Medical Information Mart for Intensive Care IV (MIMIC-IV) clinical notes dataset (5200 patients, 72,000 notes). Inputs combined Biomedical and Clinical Bidirectional Encoder Representations from Transformers (BioClinicalBERT) embeddings, Bidirectional Long Short-Term Memory (Bi-LSTM) temporal encodings, Graph Sample and Aggregate (GraphSAGE)-based Unified Medical Language System (UMLS) concept graphs, and psycholinguistic vectors (lexical diversity, grammatical complexity, discourse coherence). On the MIMIC-III hold-out set, the model achieved 99.999% accuracy, a macro F1-score of 0.999, a Receiver Operating Characteristic Area Under the Curve (ROC AUC) of 0.999, and a temporal stability variance of 0.0008. Monte Carlo cross-validation (10,000 folds) yielded $99.997\pm 0.003$% accuracy and $0.999\pm 0.001$ macro F1. Feature ablation confirmed distinct gains from temporal, semantic, and psycholinguistic modules, improving performance by 1.1% over text-only baselines. Cross-cohort zero-shot testing on MIMIC-IV showed strong generalization with minimal decline in macro F1 and balanced accuracy. Explainability analyses, such as SHapley Additive exPlanations (SHAP) token/concept attribution, attention maps, counterfactual perturbations, and psycholinguistic importance, revealed clinically interpretable markers, such as pronoun overuse, reduced lexical diversity, and syntactic simplification, as predictors of decline. Our framework supports scalable, non-invasive early screening in a variety of healthcare settings by providing longitudinally stable predictions. Full article

With artificial intelligence (AI) rapidly increasing in popularity and presence in everyday life, new applications utilizing AI are being explored across virtually all domains, from banking and healthcare to cybersecurity to generative AI for images, voice, and video content creation. With that trend comes an inherent need for increased AI capabilities. One cornerstone of AI applications is the ability of generative AI to consume documents and utilize their content to answer questions, generate new content, correlate it with other data sources, and more. No longer constrained to text alone, we now leverage multimodal AI models to help us understand visual elements within documents, such as images, tables, figures, and charts. Within this realm, capabilities have expanded exponentially from traditional Optical Character Recognition (OCR) approaches towards increasingly utilizing complex AI models for visual content analysis and understanding. Modern approaches, especially those leveraging AI, are now focusing on interpreting more complex diagrams such as flowcharts, block diagrams, Unified Modeling Language (UML) diagrams, electrical schematics, and timing diagrams. These diagram types combine text, symbols, and structured layout, making them challenging to parse and comprehend using conventional techniques. This paper presents a historical analysis and comprehensive survey of scientific literature exploring this domain of visual understanding of complex technical illustrations and diagrams. We explore the use of deep learning models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based architectures. These models, along with OCR, enable the extraction of both textual and structural information from visually complex sources. Despite these advancements, numerous challenges remain, however. These range from hallucinations, where the content extraction system produces outputs not grounded in the source image, which leads to misinterpretations, to a lack of contextual understanding of diagrammatic elements, such as arrows, grouping, and spatial hierarchy. This survey focuses on five key diagram types: flowcharts, block diagrams, UML diagrams, electrical schematics, and timing diagrams. It evaluates the effectiveness, limitations, and practical solutions—both traditional and AI-driven—that aim to enable the extraction of accurate and meaningful information from complex diagrams in a way that is trustworthy and suitable for real-world, high-accuracy AI applications. This survey reveals that virtually all approaches struggle with accurately extracting technical diagram information. It also illustrates a path forward. Pursuing research to further improve their accuracy is crucial for supporting and enabling various applications, including complex document question answering and Retrieval Augmented Generation (RAG), document-driven AI agents, accessibility applications, and automation. Full article

The development of modern production systems involves numerous interdependent disciplines, heterogeneous data sources, and frequent design iterations, making the conceptual design phase particularly complex and error-prone. Model-Based Systems Engineering (MBSE) provides a promising approach to manage this complexity by enabling consistent and structured system representations. While domain-specific modeling languages (DSMLs) can tailor MBSE methods to specific domains, existing approaches often lack standardized semantics, user guidance, and tool support to ensure consistent model creation and verification. This paper introduces a DSML framework tailored for the conceptual design of production systems, integrating both methodological guidance and standard-based domain knowledge. The approach builds upon the Software Platform Embedded Systems (SPES) framework and extends Systems Modeling Language (SysML) through the Unified Modeling Language (UML) profile mechanism, providing clear modeling constructs, viewpoint-specific diagram types, and automated consistency checks. To enhance comprehensibility and domain alignment, the framework incorporates supplementary DSMLs that capture structures and semantics from established industrial standards. The proposed method is evaluated using an aircraft production case study, demonstrating improved applicability of MBSE for the conceptual design of complex production systems. Full article

Modelling connectivity in utility networks is essential for operational management, maintenance planning, and resilience analysis. The CityGML Utility Network Application Domain Extension (UNADE) provides a detailed conceptual framework for representing utility networks; however, most existing implementations rely on relational databases, where connectivity must be reconstructed through joins rather than represented as explicit relationships. This creates challenges when managing densely connected network structures. This study introduces the UNADE–Labelled Property Graph (UNADE-LPG) model, a graph-based representation that maps the classes, relationships, and constraints defined in the UNADE Unified Modelling Language (UML) schema into nodes, edges, and properties. A conversion pipeline is developed to generate UNADE-LPG instances directly from CityGML UNADE datasets encoded in GML, enabling the population of graph databases while maintaining semantic alignment with the original schema. The approach is demonstrated through two case studies: a schematic network and a real-world water system from Frankston, Melbourne. Validation procedures, covering structural checks, topological continuity, classification behaviour, and descriptive graph statistics, confirm that the resulting graph preserves the semantic structure of the UNADE schema and accurately represents the physical connectivity of the network. An analytical path-finding query is also implemented to illustrate how the UNADE-LPG structure supports practical network-analysis tasks, such as identifying connected pipeline sequences. Overall, the findings show that the UNADE-LPG model provides a clear, standards-aligned, and operationally practical foundation for representing utility networks within graph environments, supporting future integration into digital-twin and network-analytics applications. Full article

Context: Modern software systems have become increasingly complex, making it difficult to interpret raw requirements and effectively utilize traditional tools for software design and analysis. Unified Modeling Language (UML) class diagrams are widely used to visualize and understand system architecture, but analyzing them manually, especially for large-scale systems, poses significant challenges. Objectives: This study aims to automate the analysis of UML class diagrams by assessing their complexity using a machine learning approach. The goal is to support software developers in identifying potential design issues early in the development process and to improve overall software quality. Methodology: To achieve this, this research introduces a Visual Question Answering (VQA)-based framework that integrates both computer vision and natural language processing. Vision Transformers (ViTs) are employed to extract global visual features from UML class diagrams, while the BERT language model processes natural language queries. By combining these two models, the system can accurately respond to questions related to software complexity, such as class coupling and inheritance depth. Results: The proposed method demonstrated strong performance in experimental trials. The ViT model achieved an accuracy of 0.8800, with both the F1 score and recall reaching 0.8985. These metrics highlight the effectiveness of the approach in automatically evaluating UML class diagrams. Conclusions: The findings confirm that advanced machine learning techniques can be successfully applied to automate software design analysis. This approach can help developers detect design flaws early and enhance software maintainability. Future work will explore advanced fusion strategies, novel data augmentation techniques, and lightweight model adaptations suitable for environments with limited computational resources. Full article

Aircraft design and development is complex and regulated by increasingly stringent regulatory documentation. While many disciplines manage design complexity with well-established digital tools, digital transformation of the certification process remains in the early stages of implementation. Models are often used to provide explicit structures to facilitate digital transformation. While several modeling approaches have been applied to regulatory documentation, a gap remains for an established list of requirements for developing effective models in the context of digital transformation. This paper proposes a list of requirements using a requirements elicitation framework adapted from the International Council on Systems Engineering (INCOSE) Needs and Requirements Manual. The adapted research methodology includes problem identification, needs assessment, and requirements development processes. The resulting requirements are validated against needs statements and verified against selected INCOSE requirement statement criteria. Four requirements are selected for a detailed feasibility assessment, which compares the efficacy of process mapping, Unified Modeling Language (UML), and ontological modeling methods to realize the requirements. Full article

Unified Modeling Language (UML) diagrams serve as essential tools for visualizing system structure and behavior in software design. With the emergence of Large Language Models (LLMs) that automate various phases of software development, there is growing interest in leveraging these models for UML diagram generation. This study presents a comprehensive empirical investigation into the effectiveness of GPT-4-turbo in generating four fundamental UML diagram types: Class, Deployment, Use Case, and Sequence diagrams. We developed a novel rule-based prompt-engineering framework that transforms domain scenarios into optimized prompts for LLM processing. The generated diagrams were then synthesized using PlantUML and evaluated through a rigorous survey involving 121 computer science and software engineering students across three U.S. universities. Participants assessed both the completeness and correctness of LLM-assisted and human-created diagrams by examining specific elements within each diagram type. Statistical analyses, including paired t-tests, Wilcoxon signed-rank tests, and effect size calculations, validate the significance of our findings. The results reveal that while LLM-assisted diagrams achieve meaningful levels of completeness and correctness (ranging from 61.1% to 67.7%), they consistently underperform compared to human-created diagrams. The performance gap varies by diagram type, with Sequence diagrams showing the closest alignment to human quality and Use Case diagrams exhibiting the largest discrepancy. This research contributes a validated framework for evaluating LLM-generated UML diagrams and provides empirically-grounded insights into the current capabilities and limitations of LLMs in software modeling education. Full article

In knowledge graph construction, missing facts often lead to incomplete structures, thereby limiting the performance of downstream applications. Although recent knowledge graph completion (KGC) methods based on representation learning have achieved notable progress, they still suffer from two fundamental limitations, namely the lack of structured reasoning capabilities and the inability to assess the confidence of their predictions, which often results in unreliable outputs. We propose the GLR framework, which integrates Graph Chain-of-Thought (Graph-CoT) reasoning, LoRA fine-tuning, and the P(True)-based confidence evaluation mechanism. In the KGC task, this approach effectively enhances the reasoning ability and prediction reliability of large language models (LLMs). Specifically, Graph-CoT introduces local subgraph structures to guide LLMs in performing graph-constrained, step-wise reasoning, improving their ability to model multi-hop relational patterns. Complementing this, LoRA-based fine-tuning enables efficient adaptation of LLMs to the KGC scenario with minimal computational overhead, further enhancing the model’s capability for graph-structured reasoning. Moreover, the P(True) mechanism quantifies the reliability of candidate entities, improving the robustness of ranking and the controllability of outputs, thereby enhancing the credibility and interpretability of model predictions in knowledge reasoning tasks. We conducted systematic experiments on the standard KGC datasets FB15K-237, WN18RR, and UMLS, which demonstrate the effectiveness and robustness of the GLR framework. Notably, GLR achieves a Mean Reciprocal Rank (MRR) of 0.507 on FB15K-237, marking a 6.8% improvement over the best recent instruction-tuned method, DIFT combined with CoLE (MRR = 0.439). GLR also maintains significant performance advantages on WN18RR and UMLS, verifying its effectiveness in enhancing both the structured reasoning capabilities and the prediction reliability of LLMs for KGC tasks. These results indicate that GLR offers a unified and scalable solution to enhance structure-aware reasoning and output reliability of LLMs in KGC. Full article

A persistent challenge in digital asset management is the lack of standardized models for integrating health assessment—such as the Asset Health Index (AHI)—into Digital Twins, limiting their extended implementation beyond individual projects. Asset managers in the energy sector face challenges of digitalization such as digital environment selection, employed digital modules (absence of an architecture guide) and their interconnection, sources of data, and how to automate the assessment and provide the results in a friendly decision support system. Thus, for energy systems, the integration of Asset Assessment in virtual replicas by Digital Twins is a complete way of asset management by enabling real-time monitoring, predictive maintenance, and lifecycle optimization. Another challenge in this context is how to compound in a structured assessment of asset condition, where the Asset Health Index (AHI) plays a critical role by consolidating heterogeneous data into a single, actionable indicator easy to interpret as a level of risk. This paper tries to serve as a guide against these digital and structured assessments to integrate AHI methodologies into Digital Twins for energy converters. First, the proposed AHI methodology is introduced, and after a structured data model specifically designed, orientated to a basic and economic cloud implementation architecture. This model has been developed fulfilling standardized practices of asset digitalization as the Reference Architecture Model for Industry 4.0 (RAMI 4.0), organizing asset-related information into interoperable domains including physical hierarchy, operational monitoring, reliability assessment, and risk-based decision-making. A Unified Modeling Language (UML) class diagram formalizes the data model for cloud Digital Twin implementation, which is deployed on Microsoft Azure Architecture using native Internet of Things (IoT) and analytics services to enable automated and real-time AHI calculation. This design and development has been realized from a scalable point of view and for future integration of Machine-Learning improvements. The proposed approach is validated through a case study involving three high-capacity converters in distinct operating environments, showing the model’s effective assistance in anticipating failures, optimizing maintenance strategies, and improving asset resilience. In the case study, AHI-based monitoring reduced unplanned failures by 43% and improved maintenance planning accuracy by over 30%. Full article

Despite significant efforts to promote web accessibility through the adoption of various standards and tools, the web remains inaccessible to many users. One of the main barriers is the limited knowledge of accessibility issues among website designers. This gap in expertise results in the development of websites that fail to meet accessibility standards, hindering access for people with diverse abilities and needs. In response to this challenge, this paper presents the ACG WebAcc prototype, which enables the automatic generation of accessible HTML code using a model-driven development (MDD) approach. The tool takes as input a Unified Modeling Language (UML) model, with a specific profile, and incorporates predefined Object Constraint Language (OCL) rules to ensure compliance with accessibility guidelines. By automating this process, ACG WebAcc reduces the need for extensive knowledge of accessibility standards, making it easier for designers to create accessible websites. Full article

As building information model technologies become more complex and interconnected, the validation of building information models remains critical to ensure their reliability and effectiveness in practical applications. However, most of the existing research focuses on the application of building information modeling in a single domain and lacks the collaborative validation of the overall behavior of complex dynamic systems. Therefore, how to ensure the correctness and reliability of complex building systems has become a challenging issue. To solve this problem, this paper proposes a symmetry-aware hybrid validation framework that combines Timed Automata (TA), Unified Modeling Language (UML), and AnyLogic simulation to enhance the logical correctness and practical reliability of complex building information systems; the framework inherently preserves structural and temporal symmetry between formal models and dynamic simulations, ensuring consistent validation across virtual–physical interactions. Taking the Building Information Physical Model (BIPM) as an example, the method first solves the defects of traditional methods in logical consistency and reliability validation by firstly modeling the structural model and behavioral logic of the BIPM through UML normalization, transforming the behavioral logic of the BIPM into a network of TA, and realizing the formal validation of its dynamic interaction mechanism to enhance the logical correctness and practical reliability of the complex building information system. Secondly, AnyLogic is used to map the BIPM structural model into a visual simulation model, which supports the real-time dynamic display of building system behavior and performance analysis, enhances the interpretability of the model, and provides an intuitive decision-making platform for stakeholders. Finally, an empirical study of an air conditioning system as a case study shows that the method can effectively integrate formal verification and dynamic visualization techniques, providing a scalable solution for the collaborative verification of complex building systems. Full article

Understanding and interpreting medical images, particularly radiology images, is a time-consuming task that requires specialized expertise. In this study, we developed a deep learning-based system capable of automatically assigning multiple standardized medical concepts to radiology images, leveraging deep learning models. These concepts are based on Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) and describe the radiology images in detail. Each image is associated with multiple concepts, making it a multilabel classification problem. We implemented several deep learning models, including DenseNet121, ResNet101, and VGG19, and evaluated them on the ImageCLEF 2020 Medical Concept Detection dataset. This dataset consists of radiology images with multiple CUIs associated with each image and is organized into seven categories based on their modality information. In this study, transfer learning techniques were applied, with the models initially pre-trained on the ImageNet dataset and subsequently fine-tuned on the ImageCLEF dataset. We present the evaluation results based on the F1-score metric, demonstrating the effectiveness of our approach. Our best-performing model, DenseNet121, achieved an F1-score of 0.89 on the classification of the twenty most frequent medical concepts, indicating a significant improvement over baseline methods. Full article

IT (Information Technology) support plays a major role in CPSs (cyber-physical systems). More and more IT solutions and CIS (complex information system) modules are being developed to help engineering systems to a higher level of efficiency. The different specificities of different technological environments require a very different IT approach. Increasing the efficiency of different manufacturing processes requires an appropriate architecture. The Zachman framework guidelines were applied to design a suitable framework architecture for the welding process. A literature search was conducted to explore the conditions for component matching to a complex information system, in which advanced data management and data protection are important. In order to effectively manage the standards, a dedicated module needs to be created that can be integrated into the MES-ERP (Manufacturing Execution System-Enterprise Resource Planning) architecture. The result of the study is the creation of business UML (Unified Modeling Language) and BPMN (Business Process Model and Notation) diagrams and a roadmap to start a concrete application development. The paper concludes with an example to illustrate ideas for the way forward. Full article

The unified modelling language (UML) is an industrial de facto standard for system modelling. It consists of a set of graphical notations (also known as diagrams) and has been used widely in many industrial applications. Although the graphical nature of UML is appealing to system developers, the official documentation of UML does not provide formal semantics for UML diagrams. This makes UML unsuitable for formal verification and, therefore, limited when it comes to the development of safety/security-critical systems where faults can cause damage to people, properties, or the environment. The UML activity diagram is an important UML graphical notation, which is effective in modelling the dynamic aspects of a system. This paper proposes a formal semantics for UML activity diagrams based on the calculus of context-aware ambients (CCA). An algorithm (semantic function) is proposed that maps any activity diagram onto a process in CCA, which describes the behaviours of the UML activity diagram. This process can then be executed and formally verified using the CCA simulation tool ccaPL and the CCA runtime verification tool ccaRV. Hence, design flaws can be detected and fixed early during the system development lifecycle. The pragmatics of the proposed approach are demonstrated using a case study in e-commerce. Full article